LWMSCNN-SE: A Lightweight Multi-Scale Network for Efficient Maize Disease Classification on Edge Devices
This work addresses efficient disease diagnosis for precision farming systems, but it is incremental as it combines existing techniques like multi-scale features and SE attention.
The paper tackled the problem of maize disease classification for deployment on resource-constrained edge devices by proposing LWMSCNN-SE, a lightweight CNN that achieved 96.63% accuracy with only 241,348 parameters and 0.666 GFLOPs.
Maize disease classification plays a vital role in mitigating yield losses and ensuring food security. However, the deployment of traditional disease detection models in resource-constrained environments, such as those using smartphones and drones, faces challenges due to high computational costs. To address these challenges, we propose LWMSCNN-SE, a lightweight convolutional neural network (CNN) that integrates multi-scale feature extraction, depthwise separable convolutions, and squeeze-and-Excitation (SE) attention mechanisms. This novel combination enables the model to achieve 96.63% classification accuracy with only 241,348 parameters and 0.666 GFLOPs, making it suitable for real-time deployment in field applications. Our approach addresses the accuracy--efficiency trade-off by delivering high accuracy while maintaining low computational costs, demonstrating its potential for efficient maize disease diagnosis on edge devices in precision farming systems.